diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-02-24 11:50:49 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-02-24 11:50:49 -0800 |
| commit | c5b39c4323387e59fb53184711dd113f0483b42a (patch) | |
| tree | baa80423f51f34bb7c915a1199cff255437afd25 | |
| parent | 9ca0c0bc13082aa061eee3da6b057fbacb4052e9 (diff) | |
| download | sandcrawler-c5b39c4323387e59fb53184711dd113f0483b42a.tar.gz sandcrawler-c5b39c4323387e59fb53184711dd113f0483b42a.zip | |
small tweak to americanarchivist.org URL extraction
| -rw-r--r-- | python/sandcrawler/html.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/html.py b/python/sandcrawler/html.py index 091162d..34da876 100644 --- a/python/sandcrawler/html.py +++ b/python/sandcrawler/html.py @@ -223,7 +223,7 @@ def extract_fulltext_url(html_url, html_body): # american archivist (OA) # https://americanarchivist.org/doi/abs/10.17723/aarc.62.2.j475270470145630 - if "://americanarchivist.org/doi/abs/" in html_url: + if "://americanarchivist.org/doi/" in html_url and not "/doi/pdf" in html_url: # <a href="/doi/pdf/10.17723/aarc.62.2.j475270470145630" target="_blank"> hrefs = soup.find_all('a', attrs={"target":"_blank"}) for href in hrefs: |